Connecting real-time earth and economic data to manage climate risk

Efforts to curb carbon emissions, protect biodiversity, and move toward a more sustainable relationship between humans and our planet are underpinned by data from sources such as satellites and remote sensors, historical trends, and more. The more we know about what’s going on geospatially, the better we can predict and assess the risk of climate change-related events like wildfires, droughts, and floods or track and improve air quality.

In the past, an enormous usability gap prevented this data from effecting change on a widespread basis. Before recent technology advancements, scientists would have to find, download, and write scripts to use the data. It required a great deal of time, coding knowledge, and computing power, leaving real-time insights and analysis unattainable.

For the past several years, Google Cloud has been working alongside our partners to democratize earth-based data so that it’s more accessible, usable, and actionable. Our partner Climate Engine, through their SpatiaFi platform, is one such example. Using Google Cloud components such as BigQuery, Vertex AI, and Google Earth Engine, SpatiaFi collects and processes massive amounts of Earth and geospatial data to provide private and public sector organizations insights into climate risks. By merging Earth data and asset location data, such as a farmer’s field or a highway, conditions can be monitored and analyzed in near-real time to understand the risks and impacts of climate events like floods or wildfires before, during, and after they occur. With the ability to analyze historical, current, near-term, and future time horizons, SpatiaFi provides organizations the ability to assess economic impacts, and the sustainability and resilience of their operations.

Today, institutions like BMO are working with Climate Engine to explore spatial finance tools like SpatiaFi bring location-specific environmental and economic data together to monitor and even predict how changes in one may affect the other. This can drive better risk analysis, and new financial instruments to help businesses build climate resilience into their operations.

The economic strain of climate change extends far beyond the immediate and obvious impacts of an event like a wildfire. It also affects infrastructure, transportation networks, supply chains, etc. Building resilience in this new reality requires connecting geospatial data and insights to specific locations and economies. The data relationship goes the opposite way, as well, providing opportunities for financial and other institutions to incentivize businesses to track and understand the environmental impacts of their economic decisions and enact meaningful sustainability improvements.

“Our Climate Ambition is to be our clients’ lead partner in their transition to a net-zero world. If we can harness data and information to understand the context in which our clients are operating, we can do some incredible things with finance to help them progress towards their net-zero and climate resilience goals,” says Michael Torrance, Chief Sustainability Officer of BMO. “By understanding what a changing climate might mean to our clients, we can work with them to help inform their decision making and even integrate that into financial instruments and risk-management frameworks.”

For example, leveraging data insights from SpatiaFi, BMO can help a client understand the local biodiversity impacts of a mining or factory site. Or, the bank could incentivize its clients to reduce carbon emissions, tracking progress via real-time satellite data versus requiring companies to self-report or adopt a third-party reporting system. 

Spatial finance is on the frontier of finance and technology at a crucial moment in time, notes Torrance. “The next 10 or 20 or 100 years is not going to look like the last 10, 20, or 100 years in terms of the effects of climate change. The conventional way of thinking about these problems — looking at historical data and extrapolating what we think things will be like in the future — is not a good risk-management approach. We need more real-time, forward-looking approaches. I think the opportunities provided by geospatial big data and modeling will be transformational.”